{"slug": "customizable-and-jointly-optimized-route-planning-a-deep-architecture-enabling", "title": "Customizable and Jointly Optimized Route Planning: A Deep Architecture Enabling Differentiable Shortest-Path Search", "summary": "Researchers posted arXiv:2609.19996v1, a deep architecture that jointly optimizes cost functions and a route-ranking model for customizable route planning. The system runs a multi-objective Dijkstra algorithm offline to collect Pareto optimal routes as a complete candidate set, then uses a neural network that emulates shortest-path search and route ranking in an end-to-end differentiable manner, with a loss function that optimizes a single-objective variable while holding other variables under constraints. Experiments on real-world datasets show the architecture outperforms state-of-the-art methods in route quality and customizability, according to the paper.", "body_md": "arXiv:2609.19996v1 Announce Type: new \nAbstract: With the widespread use of online navigation and ride-hailing services, achieving optimal route planning for diverse user preferences has recently attracted increasing attention. Classic graph algorithms for pathfinding use heuristic cost functions to define edge weight, thus providing no optimality guarantee of route quality. Prior data-driven approaches equating ground truth of the optimal route with user trajectory, which is however moderately influenced by the navigation service, suffers from the feedback loop problem. To address these issues, we propose a deep architecture that is able to jointly optimize cost functions and route-ranking model towards any route preference. First, we run a multi-objective Dijkstra algorithm offline to collect the set of Pareto optimal routes, deeming it as the complete candidate set. Exploiting the property of such a set, we design a neural network structure that emulates shortest-path search and route ranking in an end-to-end differentiable manner. Second, we define route preference as a task of constrained optimization of route attributes, and propose a novel loss function that optimizes a single-objective variable, with other variables strictly under constraints. We conduct extensive experiments on real-world datasets. The results show that our architecture significantly outperforms state-of-the-art methods in route quality and customizability.", "url": "https://wpnews.pro/news/customizable-and-jointly-optimized-route-planning-a-deep-architecture-enabling", "canonical_source": "https://www.machinebrief.com/news/customizable-and-jointly-optimized-route-planning-a-deep-arc-l1mv", "published_at": "2026-09-18 04:00:00+00:00", "updated_at": "2026-09-18 04:54:37.256388+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "neural-networks", "artificial-intelligence"], "entities": ["arXiv", "Dijkstra algorithm"], "alternates": {"html": "https://wpnews.pro/news/customizable-and-jointly-optimized-route-planning-a-deep-architecture-enabling", "markdown": "https://wpnews.pro/news/customizable-and-jointly-optimized-route-planning-a-deep-architecture-enabling.md", "text": "https://wpnews.pro/news/customizable-and-jointly-optimized-route-planning-a-deep-architecture-enabling.txt", "jsonld": "https://wpnews.pro/news/customizable-and-jointly-optimized-route-planning-a-deep-architecture-enabling.jsonld"}}